[vc_empty_space][vc_empty_space]
Indonesian medical question classification with pattern matching
Suwarningsih W.a, Purwarianti A.a, Supriana I.a
a School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, Indonesia
[vc_row][vc_column][vc_row_inner][vc_column_inner][vc_separator css=”.vc_custom_1624529070653{padding-top: 30px !important;padding-bottom: 30px !important;}”][/vc_column_inner][/vc_row_inner][vc_row_inner layout=”boxed”][vc_column_inner width=”3/4″ css=”.vc_custom_1624695412187{border-right-width: 1px !important;border-right-color: #dddddd !important;border-right-style: solid !important;border-radius: 1px !important;}”][vc_empty_space][megatron_heading title=”Abstract” size=”size-sm” text_align=”text-left”][vc_column_text]© 2015 IEEE.Indonesian medical question answering system requires the extraction of named entity recognition process. This research aims to propose and evaluate a systematic approach to classify Problem, Intervention, Comparison and Outcome (PICO) from the Indonesian medical sentences. We here declare that the extraction using the PICO frames for Indonesian medical sentences is the first. The advantage of PICO frame is to accelerate the classification process based on Problem Intervention, Comparison, and Outcome criteria. Our strategy here was to build a combining question term with multiple classifiers and repetition. The training and test data were generated automatically from Indonesia medical literature with 200 sentences by the exact pattern match of head words of P-I-C-O categories. This approach achieved F-measure values of 0.90 for Problem and Intervention; 0.89 for Problem, Intervention, and Comparison; 0.91 for Problem, Comparison and Outcome. It then can be concluded that by the pattern in matching criteria of the training set and the classification of PICO elements is reproducible with minimal expert intervention.[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Author keywords” size=”size-sm” text_align=”text-left”][vc_column_text]Classification process,Medical question answering,Multiple classifiers,Named entity recognition,PICO frame,Question Answering,Question classification,Semantic features[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Indexed keywords” size=”size-sm” text_align=”text-left”][vc_column_text]pattern matching,PICO frame,question answering,semantic feature[/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”Funding details” size=”size-sm” text_align=”text-left”][vc_column_text][/vc_column_text][vc_empty_space][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][vc_empty_space][megatron_heading title=”DOI” size=”size-sm” text_align=”text-left”][vc_column_text]https://doi.org/10.1109/ICACOMIT.2015.7440185[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/4″][vc_column_text]Widget Plumx[/vc_column_text][/vc_column_inner][/vc_row_inner][/vc_column][/vc_row][vc_row][vc_column][vc_separator css=”.vc_custom_1624528584150{padding-top: 25px !important;padding-bottom: 25px !important;}”][/vc_column][/vc_row]